隨著先進製程的演進，IC設計複雜度越來越高，半導體產業從原先垂直整合模式的整合元件製造商(Integrated Device Manufacturers; IDM)，到產業走向IC設計、晶圓製造、IC封裝與測試等專業化的水平模式。由於半導體產品應用於消費性產品的比例升高，消費性產品朝向輕巧方便與功率低、效能高的特性，且要求能快速上市，因此小型IC設計業者或是系統廠會委託IC設計服務公司協助部分設計來節省研發資金及加速推出產品進入市場。而現行IC設計服務公司之EDA工具資源用量是藉由公司內部人員以其自身經驗逕行估測，也因此不同的人員會產生預測不一的情況，為了避免人員之預測偏誤，本研究提出一套基於機器學習的研究架構，預測IC設計專案所需EDA工具資源進而進行資源管理。本研究使用偏最小平方迴歸法以建立EDA工具資源之預測模型，並結合領域專家知識計算出EDA工具資源使用量。本研究以台灣某IC設計服務公司為實證對象以驗證所提出方法，其研究結果顯示預測準確性相較人為預測大幅提升，將此預測應用於衡量IC設計專案的EDA工具資源使用量可以藉此提升決策品質。

With the wide range of applications such as 5G, AI, IoT, and other areas, the complexity of IC design is increasing. Due to shorten time to market, small IC design houses seek IC design service firm for IC design work to speed up the design work. Electronic design automation (EDA) tools are used by IC design companies to shorten the development. However, EDA tools and workstations are expensive and limited due to the advanced technology development of semiconductor manufacturing. Thus, the forecast accuracy of needed EDA tools resource for each design project is crucial for resource management under limited machine quantities for total resource management in IC design process.
This study aims to propose an EDA resource forecast approach based on machine learning technique for IC design projects. In particular, partial least squares regression is adopted to predict the critical parameters of EDA tools resource usage. An empirical study is conducted in an IC design service company in Taiwan to validate the proposed framework. The results show improvement in forecast accuracy that can support decision makers in IC design project resource management.

Cassel, C., Hackl, P., and Westlund, A. H. (1999), "Robustness of partial least-squares method for estimating latent variable quality structures," Journal of applied statistics, Vol. 26, No. 4, pp. 435-446.
Chien, C.-F. and Huynh, N.-T. (2018), "An Integrated Approach for IC Design R&D Portfolio Decision and Project Scheduling and a Case Study," IEEE Transactions on Semiconductor Manufacturing, Vol. 31, No. 1, pp. 76-86.
Chien, C.-F., Liu, C.-W., and Chuang, S.-C. (2017), "Analysing semiconductor manufacturing big data for root cause detection of excursion for yield enhancement," International Journal of Production Research, Vol. 55, No. 17, pp. 5095-5107.
Fu, W., Chien, C.-F., and Lin, Z.-H. (2018), "A hybrid forecasting framework with neural network and time-series method for intermittent demand in semiconductor supply chain," Proceedings of IFIP International Conference on Advances in Production Management Systems.
Geladi, P. and Kowalski, B. R. (1986), "Partial least-squares regression: a tutorial," Analytica chimica acta, Vol. 185, No., pp. 1-17.
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013), An introduction to statistical learning. Springer.
Lee, C.-Y. and Tsai, T.-L. (2019), "Data science framework for variable selection, metrology prediction, and process control in TFT-LCD manufacturing," Robotics and Computer-Integrated Manufacturing, Vol. 55, No., pp. 76-87.
Lim, H. K., Kim, Y., and Kim, M.-K. (2017), "Failure prediction using sequential pattern mining in the wire bonding process," IEEE Transactions on Semiconductor Manufacturing, Vol. 30, No. 3, pp. 285-292.
Rabaey, J. M. and Malik, S. (2008), "Challenges and solutions for late-and post-silicon design," IEEE Design & Test of Computers, Vol. 25, No. 4, pp. 296-302.
Siripitakchai, N., Miyazaki, K., and Ho, J. C. (2015), "Partnership ecosystem of IC design service companies: The case of Taiwan," Technology in Society, Vol. 43, No., pp. 199-208.
Wold, S., Sjöström, M., and Eriksson, L. (2001), "PLS-regression: a basic tool of chemometrics," Chemometrics and intelligent laboratory systems, Vol. 58, No. 2, pp. 109-130.
Zheng, J.-N., Chien, C.-F., and Lin, T.-Y. (2019), "Real Time Electronic Design Automation (EDA) Scheduling System in IC Design Industry," Proceedings of Proceedings of the 2019 International Conference on Management Science and Industrial Engineering.
林則孟 (2012), 生產計畫與管理. 華泰.
潘松 (2007), 電子設計自動化-EDA技術與VHDL. 五南.
簡禎富、許嘉裕 (2019), 大數據分析與資料挖礦. 前程文化.